Modern production lines for molded plastic parts often have automated inspection systems to detect defective parts reliably and efficiently. However, these conventional inspection systems have low flexibility and versatility, leading to difficulties when dealing with complicated requests such as when small quantities of many different parts are manufactured on the same production line. The proposed system can be implemented quickly using low-cost off-the-shelf components and does not require accurate alignment of production parts, reducing the need for manual inspections and increasing work efficiency when handling complex workloads. The inspection algorithm combines Higher-order Local Auto Correlation (HLAC) features with One-class Support Vector Machine (One-class SVM) and Principal Component Analysis (PCA) to extract, transform, and classify the differential feature vector between conforming and nonconforming plastic parts. To verify its validity and effectiveness, we compared defect detection accuracy and speed between the developed inspection system and manual inspection experimentally. Extremely high accuracy (Recall = 0.93, Specificity = 1.00) and speed (10 inspections in 30[sec]) was obtained with 7 types (1 conforming type, 6 nonconforming types) of sample parts (30 samples each). We demonstrated a 400 % increase in speed can be gained relative to manual inspection.

To alleviate social problems in agriculture such as aging and labor force shortages, automatic growth monitoring based on image measurement has been introduced to tomato cultivation in greenhouses. The overlap of leaves and fruits makes precise observations challenging. In this study, we applied context recognition to tomato growth monitoring by using a Bayesian network. The proposed method combines image recognition using convolutional networks and context recognition using Bayesian networks. It enables not only the recognition of individual tomatoes but also the evaluation of tomato plants. An accurate number of tomatoes and the condition of the stocks can be estimated based on the number of ripe and unripened tomatoes in addition to their density information. The verification experiments clarified that a more accurate number of tomatoes could be estimated than with simple tomato detection, and the stock states could also be evaluated correctly. Compared to conventional methods, the method used in this study has improved tomato decision accuracy by 23%.

Static electricity-induced luminescence (SEL) materials exhibit luminescence in response to minute electrical charges and therefore have potential for application in self-powered charge-detection sensors that operate without an external power source. However, important aspects of their luminescence mechanism and the associated material properties remain insufficiently understood. In this study, SEL films based on SrAl₂O₄:Eu²⁺ were evaluated, and the effects of SrAl₂O₄:Eu²⁺ concentration and applied voltage on the luminescence behavior were quantitatively investigated. The results showed that the SEL intensity increased in proportion to the square of the applied voltage, while the SEL luminescence area increased monotonically with increasing voltage. These results suggest that the SEL intensity and SEL area may reflect the amount of discharge–charge from the needle electrode and the charge distribution on the film surface, respectively. In addition, increasing the SEL phosphor content enhanced the luminescence intensity, whereas no significant effect was observed on the relative change in luminescence area with applied voltage. Collectively, these findings provide fundamental insights for the design of charge-detection sensors based on SrAl₂O₄:Eu²⁺.

Nonwoven electret fabrics significantly improve the performance of filters used in various commercial products. In this study, we employed a no-contact, high-spatial-resolution surface potential distribution measurement system to verify the accuracy of evaluation methods for the surface charge distribution of nonwoven electret fabrics. Nonwoven electret fabric samples were fabricated through corona discharging, and their surface potential distributions were measured nondestructively. Thereafter, positively and negatively charged toners were dispersed to visualize the surface charge polarity of the sample. The results obtained using two measurement methods were analyzed through pixel-based analysis and higher-order local autocorrelation (HLAC) feature extraction. The results of the pixel-based analysis aligned with the charge distribution by 70–80 %, and the HLAC feature-based analysis indicated a high correlation between the overall surface charge distribution and the gray values of the images obtained using both measurement methods. These findings indicate that the proposed surface potential measurement system can effectively evaluate the surface charge distribution of nonwoven electret fabrics.